metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: bart_test_p2
results: []
bart_test_p2
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0481
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1378 | 0.34 | 500 | 0.1011 |
| 0.0977 | 0.67 | 1000 | 0.0810 |
| 0.0802 | 1.01 | 1500 | 0.0678 |
| 0.0533 | 1.35 | 2000 | 0.0639 |
| 0.0534 | 1.69 | 2500 | 0.0560 |
| 0.0435 | 2.02 | 3000 | 0.0531 |
| 0.0303 | 2.36 | 3500 | 0.0544 |
| 0.0323 | 2.7 | 4000 | 0.0521 |
| 0.0254 | 3.04 | 4500 | 0.0488 |
| 0.022 | 3.37 | 5000 | 0.0490 |
| 0.0199 | 3.71 | 5500 | 0.0480 |
| 0.0142 | 4.05 | 6000 | 0.0477 |
| 0.0134 | 4.39 | 6500 | 0.0481 |
| 0.0113 | 4.72 | 7000 | 0.0481 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0.dev20230621+cu117
- Datasets 2.17.0
- Tokenizers 0.15.0